Conditional Rate-Distortion-Perception Trade-Off

Recent advances in machine learning-aided lossy compression are incorporating perceptual fidelity into the rate-distortion theory. In this paper, we study the rate-distortion-perception trade-off when the perceptual quality is measured by the total variation distance between the empirical and product distributions of the discrete memoryless source and its reconstruction. We consider the general setting, where two types of resources are available at both the encoder and decoder: a common side information sequence, correlated with the source sequence, and common randomness. We show that the region under the strong perceptual constraint is a subset of that for the weaker empirical perceptual constraint. When sufficient common randomness is provided, the required communication rate is the minimum conditional mutual information such that the distortion and perceptual constraints are satisfied. The coding scheme in the proof of achievability takes advantage of the likelihood encoder.